KR102525978B1 - Method and apparatus for providing mock exam service to a test taker terminal using a neural network - Google Patents

Abstract

Embodiments propose a method and apparatus for providing a mock test service to a test taker terminal using a neural network. The method according to one embodiment includes the steps of: receiving an application message; creating an online examination center at an opening date and opening time; receiving an entry message to an online testing site from the test taker terminal; providing information about a real-time mock test to the test taker terminal; and transmitting scores for answers for each section of the test taker terminal to the test taker terminal.

Description

METHOD AND APPARATUS FOR PROVIDING MOCK EXAM SERVICE TO A TEST TAKER TERMINAL USING A NEURAL NETWORK}

Embodiments of the present disclosure relate to a technology for providing a mock test service to a test taker terminal, and to a technology for providing a mock test service to a test taker terminal using a neural network.

Meanwhile, due to the international popularity of the Korean Wave, foreigners' interest and demand for the Test of Proficiency in Korean (TOPIK) is increasing. TOPIK is a Korean proficiency test administered by the National Institute for International Education, a national institution, and is directly operated by the state.

Currently, TOPIK test takers residing abroad rarely have academies that conduct mock tests related to TOPIK, so most test takers prepare for TOPIK by purchasing a separate TOPIK mock test booklet and solving it personally.

Therefore, there is a need for a service that provides an environment similar to that of solving the TOPIK mock test online, and provides quick and accurate feedback to test takers on the answer of the TOPIK mock test by using a scoring model and a correction model through a neural network.

Embodiments of the present disclosure may provide a method and apparatus for providing a mock test service to test taker terminals using a neural network.

Technical tasks to be achieved in the embodiments are not limited to those mentioned above, and other technical tasks not mentioned will be considered by those skilled in the art from various embodiments to be described below. can

A method in which a server provides a mock test service to a test taker terminal using a neural network according to an embodiment includes receiving an application message requesting a mock test related to the Korean Proficiency Test from the test taker terminal, and receiving the request message from the test taker terminal. includes identification information of the candidate terminal, location information of the candidate terminal, and information on the type of mock test, and the information on the type of mock test is the test type of mock test related to the Korean Proficiency Test and the mock test related to the Korean Proficiency Test Including the progress type, the test type of the mock test related to the Korean Proficiency Test includes a first type including a listening area and a reading area and a second type including a listening area, a reading area, and a writing area, and the Korean language proficiency test The mock test related to the test includes a first progress type and a second progress type, and the first progress type allows the test taker terminal to determine the opening date and opening time of the online test center, and the first progress type allows the test taker terminal to 2 Progress type is based on the fact that the authority to determine the opening date and opening time of the online test center is allowed to the server, and the type of mock test related to the Korean language proficiency test corresponds to the second type, Creating an ongoing online test room at a preset opening date and opening time, receiving an admission message for the online test center from the test taker terminal within a preset time from the preset opening time, and connecting the test taker terminal and the server Based on this, information on the real-time mock test pre-entered into the server is provided to the test taker terminal, answers for each area of the test taker terminal are received from the test taker terminal, and the test type of the mock test related to the Korean language proficiency test and the above The method may include determining a score for an answer for each area of the test taker terminal based on a provisional score for the answer for each area of the test taker terminal, and transmitting the score for the answer for each area of the test taker terminal to the test taker terminal. . A false scoring score for the writing area among the answers for each area of the test taker terminal may be determined through a false scoring model using a first neural network based on the answer to the writing area of the test taker terminal after the real-time mock test is finished.

For example, based on the fact that the test type corresponds to the second type, and an option to correct an answer to a writing area is included in paid options for the test taker terminal identified according to the identification information of the test taker terminal. , An answer to the writing area of the test taker terminal in which the expected correction/removal area is displayed may be transmitted from the server to the corrector terminal. A correction copy for the writing area may be received from the server by the correction person terminal. An edited version of the writing area may be transmitted from the server to the candidate terminal. The predicted correction area may be determined through an correction prediction model using a second neural network based on an answer to the writing area of the test taker terminal.

For example, based on the connection between the test taker terminal and the server, information about a type of voice file for a listening area may be transmitted to the test taker terminal. The type of the voice file may include a general sound quality type and an actual sound quality type in which the voice file is processed similarly to an actual test hall. The audio file for the listening area may be reproduced as the type of the audio file for the listening area selected by the test taker terminal. Based on the fact that the mock test related to the Korean language proficiency test corresponds to the second progress type, the operation button for the audio file for the listening area may be deactivated. The maximum number of questions displayed on the screen of questions transmitted to the test taker terminal after the test taker terminal and the server are connected according to the number of test taker terminals connected to the online test center, the capability of the server, and the communication state between the server and the test taker terminal. number can be determined.

For example, based on the user of the test taker terminal performing a hovering operation within a preset height for a question option on the question screen of the reading area, the option may be displayed in a blank area associated with the question option. can A user interface for selecting a method of inputting an answer to a question screen in the writing area may be provided to the test taker terminal. The method of inputting an answer to the question screen of the writing area may include a first method of inputting an answer using a text field of the test taker terminal and a second method of inputting an image provided by the test taker terminal. The image provided by the test taker terminal may be an image directly written by a user of the test taker terminal.

For example, based on the fact that the test type corresponds to the second type, provisional scoring points for answers in the writing area of the test taker terminal may be transmitted to the scorer terminal. A final score for an answer in the writing area of the test taker terminal may be transmitted to the server from the scorer terminal. Scores for answers in the writing area of the test taker terminal may be determined as final scores for answers for each area of the test taker terminal.

The false scoring model may be a gated recurrent unit (GRU) based neural network model. The first neural network may include a first input layer, one or more first hidden layers, and a first output layer. Data for learning each of the first neural networks consisting of a plurality of texts, a plurality of answer texts, and correct answer points is input to the first input layer of the first neural network, and the one or more first hidden layers and A first output vector is output through one output layer, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value is output using a first loss function that compares the first correct answer vector for the learning data of , and the parameters of the first neural network are learned in a direction in which the first loss value becomes smaller. The false scoring point A model can be created.

The expected correction area may be an area where texts corresponding to a plurality of error types are located in an answer to the writing area of the test taker terminal. The plurality of error types may include spaces errors, punctuation errors, rhetorical errors, spelling and grammar errors, letter deletion errors, letter addition errors, letter substitution errors, and letter separation errors.

The correction prediction model may include a bidirectional long short-term memory (LSTM) model. The second neural network may include a second input layer, one or more second hidden layers, and a second output layer. Data for learning of each second neural network composed of a plurality of texts and a plurality of texts for each of a plurality of correct answer types is input to the second input layer of the second neural network, and the one or more second hidden A second output vector is output through a layer and a second output layer, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is used as the second output vector. A second loss value is output using a second loss function that compares a vector with a second correct answer vector for each learning data, and parameters of the second neural network are learned in a direction in which the second loss value decreases. , the correction prediction model may be generated.

Additionally, for example, the first preset time may be determined by the following equation.

은 상기 응시자 단말과 관련된 국가의 가중치이고, 상기 n_a는 상기 모의고사에 신청한 응시자 단말의 개수이고, 상기 n_m은 모의고사에 신청하는 응시자 단말의 평균 개수이고, 상기 t_c는 상기 서버의 시스템을 점검하기 위한 시간이고, 상기

는 상기 모의고사의 유형과 관련된 가중치이고, 상기 k는 상기 모의고사에서 듣기 영역의 문항 개수이고, 상기 t_i는 i번째 듣기 영역의 문항에 대한 음성 파일의 재생시간일 수 있다.In the above formula, the t ₁ is the preset first time,

is the weight of the country related to the test taker terminal, n _a is the number of test taker terminals applying for the mock test, n _m is the average number of test taker terminals applying for the mock test, and t _c is the system of the server It is time to check, and

is a weight related to the mock test type, k is the number of questions in the listening section of the mock test, and t _i may be a playback time of an audio file for an i-th listening section question.

Additionally, for example, the maximum number of questions displayed on the screen of questions transmitted to the test taker terminal may be determined by the following equation.

In the above equation, n _p is the maximum number of questions displayed on the item screen, n is the number of test taker terminals connected to the server, t _r is the average response time for test taker terminals of the server, and n _avg is the average number of test taker terminals connected to the server, t _th is a reference response time, the RSRP is a value related to the communication state of the test taker terminal, and the RSRP _th is a reference for a value related to the communication state value, and n _d may be a basic value for the maximum number.

According to the embodiments, the server provides an environment similar to taking the Korean language proficiency test directly to the test taker terminal by limiting the entrance time to the online test center as in the real test and controlling the progress of the mock test related to the Korean language proficiency test. can do.

According to embodiments, the server performs provisional scoring on an answer in the writing area prepared by the test taker terminal through a provisional scoring model using a neural network, and performs provisional scoring on an answer in the writing area prepared by the test taker terminal through a correction prediction model using a neural network. By estimating the correction area, it is possible to assist the grader terminal performing scoring on the answer to score more objectively, and support the corrector terminal performing correction/deletion on the answer to quickly and accurately correct and delete.

Effects obtainable from the embodiments are not limited to the effects mentioned above, and other effects not mentioned are clearly derived and understood by those skilled in the art based on the detailed description below. It can be.

BRIEF DESCRIPTION OF THE DRAWINGS Included as part of the detailed description to aid understanding of the embodiments, the accompanying drawings provide various embodiments and, together with the detailed description, describe technical features of the various embodiments.
1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.
2 is a diagram showing the configuration of a program according to an embodiment.
3 illustrates a method in which a server provides a mock test service to test taker terminals using a neural network according to an embodiment.
4 is a diagram of a false scoring model according to an embodiment.
5 is a flowchart of a method for a server to provide a mock test service to a test taker terminal using a neural network according to an embodiment.
6 is a block diagram illustrating a configuration of a server according to an exemplary embodiment.

The following embodiments combine elements and features of the embodiments in a predetermined form. Each component or feature may be considered optional unless explicitly stated otherwise. Each component or feature may be implemented in a form not combined with other components or features. In addition, various embodiments may be configured by combining some components and/or features. The order of operations described in various embodiments may be changed. Some components or features of one embodiment may be included in another embodiment, or may be replaced with corresponding components or features of another embodiment.

In the description of the drawings, procedures or steps that may obscure the gist of various embodiments are not described, and procedures or steps that can be understood by those skilled in the art are not described. did

Throughout the specification, when a part is said to "comprising" or "including" a certain element, it means that it may further include other elements, not excluding other elements, unless otherwise stated. do. In addition, terms such as “… unit”, “… unit”, and “module” described in the specification mean a unit that processes at least one function or operation, which is hardware or software or a combination of hardware and software. can be implemented as Also, “a or an”, “one”, “the” and like terms are used herein in the context of describing various embodiments (particularly in the context of the claims below). Unless otherwise indicated or clearly contradicted by context, both the singular and the plural can be used.

Hereinafter, embodiments according to various embodiments will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The detailed description set forth below in conjunction with the accompanying drawings is intended to describe exemplary embodiments of various embodiments, and is not intended to represent a single embodiment.

In addition, specific terms used in various embodiments are provided to help understanding of various embodiments, and the use of these specific terms may be changed into other forms without departing from the technical spirit of various embodiments. .

1 is a diagram illustrating a configuration of an electronic device according to an exemplary embodiment.

1 is a block diagram of an electronic device 101 within a network environment 100, according to various embodiments. Referring to FIG. 1 , in a network environment 100, an electronic device 101 communicates with an electronic device 102 through a first network 198 (eg, a short-range wireless communication network) or through a second network 199. It may communicate with at least one of the electronic device 104 or the server 108 through (eg, a long-distance wireless communication network). According to one embodiment, the electronic device 101 may communicate with the electronic device 104 through the server 108 . According to an embodiment, the electronic device 101 includes a processor 120, a memory 130, an input module 150, an audio output module 155, a display module 160, an audio module 170, a sensor module ( 176), interface 177, connection terminal 178, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196 , or the antenna module 197 may be included. In some embodiments, in the electronic device 101, at least one of these components (eg, the connection terminal 178) may be omitted or one or more other components may be added. In some embodiments, some of these components (eg, sensor module 176, camera module 180, or antenna module 197) are integrated into a single component (eg, display module 160). It can be. The electronic device 101 may also be referred to as a client, terminal, or peer.

The processor 120, for example, executes software (eg, the program 140) to cause at least one other component (eg, hardware or software component) of the electronic device 101 connected to the processor 120. It can control and perform various data processing or calculations. According to one embodiment, as at least part of data processing or operation, the processor 120 transfers instructions or data received from other components (e.g., sensor module 176 or communication module 190) to volatile memory 132. , processing commands or data stored in the volatile memory 132 , and storing resultant data in the non-volatile memory 134 . According to one embodiment, the processor 120 may include a main processor 121 (eg, a central processing unit or an application processor) or a secondary processor 123 (eg, a graphic processing unit, a neural network processing unit ( NPU: neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, when the electronic device 101 includes the main processor 121 and the auxiliary processor 123, the auxiliary processor 123 may use less power than the main processor 121 or be set to be specialized for a designated function. can The secondary processor 123 may be implemented separately from or as part of the main processor 121 .

The secondary processor 123 may, for example, take the place of the main processor 121 while the main processor 121 is in an inactive (eg, sleep) state, or the main processor 121 is active (eg, running an application). ) state, together with the main processor 121, at least one of the components of the electronic device 101 (eg, the display module 160, the sensor module 176, or the communication module 190) It is possible to control at least some of the related functions or states. According to one embodiment, the auxiliary processor 123 (eg, image signal processor or communication processor) may be implemented as part of other functionally related components (eg, camera module 180 or communication module 190). there is. According to an embodiment, the auxiliary processor 123 (eg, a neural network processing device) may include a hardware structure specialized for processing an artificial intelligence model.

AI models can be created through machine learning. Such learning may be performed, for example, in the electronic device 101 itself where the artificial intelligence model is performed, or may be performed through a separate server (eg, the server 108). The learning algorithm may include, for example, supervised learning, unsupervised learning, semi-supervised learning or reinforcement learning, but in the above example Not limited. The artificial intelligence model may include a plurality of artificial neural network layers. Artificial neural networks include deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), restricted boltzmann machines (RBMs), deep belief networks (DBNs), bidirectional recurrent deep neural networks (BRDNNs), It may be one of deep Q-networks or a combination of two or more of the foregoing, but is not limited to the foregoing examples. The artificial intelligence model may include, in addition or alternatively, software structures in addition to hardware structures.

The memory 130 may store various data used by at least one component (eg, the processor 120 or the sensor module 176) of the electronic device 101 . The data may include, for example, input data or output data for software (eg, program 140) and commands related thereto. The memory 130 may include volatile memory 132 or non-volatile memory 134 .

The program 140 may be stored as software in the memory 130 and may include, for example, an operating system 142 , middleware 144 , or an application 146 .

The input module 150 may receive a command or data to be used by a component (eg, the processor 120) of the electronic device 101 from the outside of the electronic device 101 (eg, a user). The input module 150 may include, for example, a microphone, a mouse, a keyboard, a key (eg, a button), or a digital pen (eg, a stylus pen or a touch pen).

The sound output module 155 may output sound signals to the outside of the electronic device 101 . The sound output module 155 may include, for example, a speaker or a receiver. The speaker can be used for general purposes such as multimedia playback or recording playback. A receiver may be used to receive an incoming call. According to one embodiment, the receiver may be implemented separately from the speaker or as part of it.

The display module 160 may visually provide information to the outside of the electronic device 101 (eg, a user). The display module 160 may include, for example, a display, a hologram device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module 160 may include a touch sensor set to detect a touch or a pressure sensor set to measure the intensity of force generated by the touch.

The audio module 170 may convert sound into an electrical signal or vice versa. According to one embodiment, the audio module 170 acquires sound through the input module 150, the sound output module 155, or an external electronic device connected directly or wirelessly to the electronic device 101 (eg: Sound may be output through the electronic device 102 (eg, a speaker or a headphone).

The sensor module 176 detects an operating state (eg, power or temperature) of the electronic device 101 or an external environmental state (eg, a user state), and generates an electrical signal or data value corresponding to the detected state. can do. According to one embodiment, the sensor module 176 may include, for example, a gesture sensor, a gyro sensor, an air pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a bio sensor, It may include a temperature sensor, humidity sensor, or light sensor.

The interface 177 may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device 101 to an external electronic device (eg, the electronic device 102). According to one embodiment, the interface 177 may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

The connection terminal 178 may include a connector through which the electronic device 101 may be physically connected to an external electronic device (eg, the electronic device 102). According to one embodiment, the connection terminal 178 may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (eg, a headphone connector).

The haptic module 179 may convert electrical signals into mechanical stimuli (eg, vibration or motion) or electrical stimuli that a user may perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module 179 may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

The camera module 180 may capture still images and moving images. According to one embodiment, the camera module 180 may include one or more lenses, image sensors, image signal processors, or flashes.

The power management module 188 may manage power supplied to the electronic device 101 . According to one embodiment, the power management module 188 may be implemented as at least part of a power management integrated circuit (PMIC), for example.

The battery 189 may supply power to at least one component of the electronic device 101 . According to one embodiment, the battery 189 may include, for example, a non-rechargeable primary cell, a rechargeable secondary cell, or a fuel cell.

The communication module 190 is a direct (eg, wired) communication channel or a wireless communication channel between the electronic device 101 and an external electronic device (eg, the electronic device 102, the electronic device 104, or the server 108). Establishment and communication through the established communication channel may be supported. The communication module 190 may include one or more communication processors that operate independently of the processor 120 (eg, an application processor) and support direct (eg, wired) communication or wireless communication. According to one embodiment, the communication module 190 is a wireless communication module 192 (eg, a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module 194 (eg, : a local area network (LAN) communication module or a power line communication module). Among these communication modules, a corresponding communication module is a first network 198 (eg, a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network 199 (eg, legacy It may communicate with the external electronic device 104 through a cellular network, a 5G network, a next-generation communication network, the Internet, or a telecommunications network such as a computer network (eg, a LAN or a WAN). These various types of communication modules may be integrated as one component (eg, a single chip) or implemented as a plurality of separate components (eg, multiple chips). The wireless communication module 192 uses subscriber information (eg, International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module 196 within a communication network such as the first network 198 or the second network 199. The electronic device 101 may be identified or authenticated.

The wireless communication module 192 may support a 5G network after a 4G network and a next-generation communication technology, for example, NR access technology (new radio access technology). NR access technologies include high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and access of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low latency (URLLC)). -latency communications)) can be supported. The wireless communication module 192 may support a high frequency band (eg, mmWave band) to achieve a high data rate, for example. The wireless communication module 192 uses various technologies for securing performance in a high frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), and full-dimensional multiplexing. Technologies such as input/output (FD-MIMO: full dimensional MIMO), array antenna, analog beam-forming, or large scale antenna may be supported. The wireless communication module 192 may support various requirements defined for the electronic device 101, an external electronic device (eg, the electronic device 104), or a network system (eg, the second network 199). According to one embodiment, the wireless communication module 192 is a peak data rate for eMBB realization (eg, 20 Gbps or more), a loss coverage for mMTC realization (eg, 164 dB or less), or a U-plane latency for URLLC realization (eg, Example: downlink (DL) and uplink (UL) each of 0.5 ms or less, or round trip 1 ms or less) may be supported.

The antenna module 197 may transmit or receive signals or power to the outside (eg, an external electronic device). According to one embodiment, the antenna module 197 may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (eg, PCB). According to one embodiment, the antenna module 197 may include a plurality of antennas (eg, an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network such as the first network 198 or the second network 199 is selected from the plurality of antennas by the communication module 190, for example. can be chosen A signal or power may be transmitted or received between the communication module 190 and an external electronic device through the selected at least one antenna. According to some embodiments, other components (eg, a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module 197 in addition to the radiator.

According to various embodiments, the antenna module 197 may form a mmWave antenna module. According to one embodiment, the mmWave antenna module includes a printed circuit board, an RFIC disposed on or adjacent to a first surface (eg, a lower surface) of the printed circuit board and capable of supporting a designated high frequency band (eg, mmWave band); and a plurality of antennas (eg, array antennas) disposed on or adjacent to a second surface (eg, a top surface or a side surface) of the printed circuit board and capable of transmitting or receiving signals of the designated high frequency band. can do.

At least some of the components are connected to each other through a communication method between peripheral devices (eg, a bus, general purpose input and output (GPIO), serial peripheral interface (SPI), or mobile industry processor interface (MIPI)) and signal ( e.g. commands or data) can be exchanged with each other.

According to an embodiment, commands or data may be transmitted or received between the electronic device 101 and the external electronic device 104 through the server 108 connected to the second network 199 . Each of the external electronic devices 102 or 104 may be the same as or different from the electronic device 101 . According to an embodiment, all or part of operations executed in the electronic device 101 may be executed in one or more external electronic devices among the external electronic devices 102 , 104 , or 108 . For example, when the electronic device 101 needs to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device 101 instead of executing the function or service by itself. Alternatively or additionally, one or more external electronic devices may be requested to perform the function or at least part of the service. One or more external electronic devices receiving the request may execute at least a part of the requested function or service or an additional function or service related to the request, and deliver the execution result to the electronic device 101 . The electronic device 101 may provide the result as at least part of a response to the request as it is or additionally processed. To this end, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device 101 may provide an ultra-low latency service using, for example, distributed computing or mobile edge computing. In another embodiment, the external electronic device 104 may include an internet of things (IoT) device. Server 108 may be an intelligent server using machine learning and/or neural networks. According to one embodiment, the external electronic device 104 or server 108 may be included in the second network 199 . The electronic device 101 may be applied to intelligent services (eg, smart home, smart city, smart car, or health care) based on 5G communication technology and IoT-related technology.

The server 108 is connected to the electronic device 101 and can provide a service to the connected electronic device 101 . In addition, the server 108 may proceed with a membership sign-up procedure, store and manage various types of information of users subscribed as members, and provide various purchase and payment functions related to services. In addition, the server 108 may share execution data of service applications executed in each of the plurality of electronic devices 101 in real time so that the service can be shared among users. This server 108 may have the same configuration as a conventional web server or service server in terms of hardware. However, in terms of software, it may include a program module that is implemented through any language such as C, C++, Java, Python, Golang, or kotlin and performs various functions. In addition, the server 108 is generally connected to an unspecified number of clients and/or other servers through an open computer network such as the Internet, and receives requests from clients or other servers to perform tasks and derives and provides work results. It means a computer system and the computer software (server program) installed for it. In addition, the server 108, in addition to the above-described server program, a series of application programs operating on the server 108 and various databases (DB: Database, hereinafter referred to as It should be understood as a broad concept including DB"). Accordingly, the server 108 classifies member registration information and various information and data about games, stores them in a DB, and manages them. This DB may be implemented inside or outside the server 108 . In addition, the server 108 may be implemented using server programs that are provided in various ways according to operating systems such as Windows, Linux, UNIX, and Macintosh on general server hardware, As a representative example, a web service can be implemented using IIS (Internet Information Server) used in a Windows environment and CERN, NCSA, APPACH, TOMCAT, etc. used in a Unix environment. In addition, the server 108 may interoperate with an authentication system and a payment system for user authentication of services or payment for purchases related to services.

The first network 198 and the second network 199 are a connection structure capable of exchanging information between nodes such as terminals and servers, or a network connecting the server 108 and the electronic devices 101 and 104. means (Network). The first network 198 and the second network 199 include Internet, Local Area Network (LAN), Wireless Local Area Network (Wireless Local Area Network), Wide Area Network (WAN), Personal Area Network (PAN), and 3G , 4G, LTE, 5G, Wi-Fi, etc., but are not limited thereto. The first network 198 and the second network 199 may be closed first networks 198 and second networks 199 such as LAN and WAN, but are preferably open such as the Internet. The Internet includes protocols such as the TCP/IP protocol, TCP, and User Datagram Protocol (UDP), and various services that exist in the upper layer, such as HTTP (HyperText Transfer Protocol), Telnet, FTP (File Transfer Protocol), and DNS (Domain Name System). ), Simple Mail Transfer Protocol (SMTP), Simple Network Management Protocol (SNMP), Network File Service (NFS), and Network Information Service (NIS). ) structure.

A database may have a general data structure implemented in a storage space (hard disk or memory) of a computer system using a database management program (DBMS). The database may have a data storage form in which data can be freely searched for (extracted), deleted, edited, added, and the like. Databases are relational database management systems (RDBMS) such as Oracle, Informix, Sybase, and DB2, or object-oriented database management such as Gemston, Orion, and O2. It can be implemented according to the purpose of an embodiment of the present disclosure using a system (OODBMS) and XML Native Databases such as Excelon, Tamino, and Sekaiju, and its functions may have appropriate fields or elements to achieve.

2 is a diagram showing the configuration of a program according to an embodiment.

2 is a block diagram 200 illustrating a program 140 according to various embodiments. According to one embodiment, the program 140 includes an operating system 142, middleware 144, or an application 146 executable in the operating system 142 for controlling one or more resources of the electronic device 101. can include The operating system 142 may include, for example, Android™, iOS™, Windows™, Symbian™ or Tizen™. At least some of the programs 140 are, for example, preloaded in the electronic device 101 at the time of manufacture, or when used by a user, an external electronic device (eg, the electronic device 102 or 104), or a server ( 108)) can be downloaded or updated. All or part of program 140 may include a neural network.

The operating system 142 may control management (eg, allocation or reclamation) of one or more system resources (eg, process, memory, or power) of the electronic device 101 . Operating system 142 may additionally or alternatively include other hardware devices of electronic device 101 , such as input module 150 , sound output module 155 , display module 160 , audio module 170 . , sensor module 176, interface 177, haptic module 179, camera module 180, power management module 188, battery 189, communication module 190, subscriber identification module 196, or It may include one or more driver programs for driving the antenna module 197.

The middleware 144 may provide various functions to the application 146 so that the function or information provided from one or more resources of the electronic device 101 may be used by the application 146 . The middleware 144 includes, for example, the application manager 201, the window manager 203, the multimedia manager 205, the resource manager 207, the power manager 209, the database manager 211, and the package manager 213. ), connectivity manager 215, notification manager 217, location manager 219, graphics manager 221, security manager 223, call manager 225, or voice recognition manager 227. can

The application manager 201 may manage the life cycle of the application 146 , for example. The window manager 203 may manage one or more GUI resources used in a screen, for example. The multimedia manager 205 identifies, for example, one or more formats necessary for reproducing media files, and encodes or decodes a corresponding media file among the media files using a codec suitable for the selected format. can be done The resource manager 207 may manage a source code of the application 146 or a memory space of the memory 130 . The power manager 209 may manage, for example, the capacity, temperature, or power of the battery 189, and determine or provide related information necessary for the operation of the electronic device 101 by using corresponding information among them. . According to an embodiment, the power manager 209 may interoperate with a basic input/output system (BIOS) (not shown) of the electronic device 101 .

The database manager 211 may create, search, or change a database to be used by the application 146, for example. The package manager 213 may manage installation or update of applications distributed in the form of package files, for example. The connectivity manager 215 may manage, for example, a wireless connection or a direct connection between the electronic device 101 and an external electronic device. The notification manager 217 may provide a function for notifying a user of occurrence of a designated event (eg, an incoming call, message, or alarm), for example. The location manager 219 may manage location information of the electronic device 101, for example. The graphic manager 221 may manage, for example, one or more graphic effects to be provided to a user or a user interface related thereto.

Security manager 223 may provide system security or user authentication, for example. The telephony manager 225 may manage, for example, a voice call function or a video call function provided by the electronic device 101 . The voice recognition manager 227 transmits, for example, the user's voice data to the server 108, and at least partially based on the voice data, a command corresponding to a function to be performed in the electronic device 101; Alternatively, text data converted at least partially based on the voice data may be received from the server 108 . According to one embodiment, the middleware 244 may dynamically delete some existing components or add new components. According to one embodiment, at least part of the middleware 144 may be included as part of the operating system 142 or may be implemented as separate software different from the operating system 142 .

The application 146 includes, for example, a home 251, a dialer 253, an SMS/MMS 255, an instant message (IM) 257, a browser 259, a camera 261, and an alarm 263. , Contacts (265), Voice Recognition (267), Email (269), Calendar (271), Media Player (273), Albums (275), Watch (277), Health (279) (e.g. exercise or blood sugar) measurement of biometric information) or environmental information 281 (eg, measurement of atmospheric pressure, humidity, or temperature information). According to an embodiment, the application 146 may further include an information exchange application (not shown) capable of supporting information exchange between the electronic device 101 and an external electronic device. The information exchange application may include, for example, a notification relay application configured to transmit designated information (eg, a call, message, or alarm) to an external electronic device, or a device management application configured to manage an external electronic device. there is. The notification relay application, for example, transmits notification information corresponding to a designated event (eg, mail reception) generated in another application (eg, the email application 269) of the electronic device 101 to an external electronic device. can Additionally or alternatively, the notification relay application may receive notification information from an external electronic device and provide the notification information to the user of the electronic device 101 .

The device management application is, for example, a power source (eg, turn-on or turn-off) of an external electronic device that communicates with the electronic device 101 or some component thereof (eg, a display module or a camera module of the external electronic device). ) or functions (eg brightness, resolution, or focus). The device management application may additionally or alternatively support installation, deletion, or update of an application operating in an external electronic device.

Throughout this specification, a neural network, a neural network, and a network function may be used interchangeably. A neural network may consist of a set of interconnected computational units, which may be generally referred to as “nodes”. These “nodes” may also be referred to as “neurons”. A neural network includes at least two or more nodes. Nodes (or neurons) constituting neural networks may be interconnected by one or more “links”.

In a neural network, two or more nodes connected through a link may form a relative relationship of an input node and an output node. The concept of an input node and an output node is relative, and any node in an output node relationship with one node may have an input node relationship with another node, and vice versa. As described above, the input node to output node relationship can be created around the link. More than one output node can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the output node may be determined based on data input to the input node. Here, a node interconnecting the input node and the output node may have a weight. The weight may be variable, and may be changed by a user or an algorithm in order for the neural network to perform a desired function. For example, when one or more input nodes are interconnected by respective links to one output node, the output node is set to a link corresponding to values input to input nodes connected to the output node and respective input nodes. An output node value may be determined based on the weight.

As described above, in a neural network, two or more nodes are interconnected through one or more links to form an input node and output node relationship in the neural network. Characteristics of the neural network may be determined according to the number of nodes and links in the neural network, an association between the nodes and links, and a weight value assigned to each link. For example, when there are two neural networks having the same number of nodes and links and different weight values between the links, the two neural networks may be recognized as different from each other.

3 illustrates a method in which a server provides a mock test service to test taker terminals using a neural network according to an embodiment. One embodiment of FIG. 3 may be combined with various embodiments of the present disclosure.

Referring to FIG. 3 , in step S301, the server may receive an application message requesting a mock test related to the Korean language proficiency test from the test taker terminal.

The server may be a server that operates a service that provides mock tests related to the Korean Proficiency Test online, and guides and operates mock tests related to the Korean Proficiency Test in various countries in the language of the respective countries. For example, the server may be server 108 of FIG. 1 .

The test taker terminal may be a terminal for taking a mock test related to the Korean language proficiency test. For example, the test taker terminal may be the electronic device 101 of FIG. 1 .

The application message may include identification information of the test taker terminal, location information of the test taker terminal, and information on the type of mock test. Here, the identification information may include information for identifying the candidate terminal and contact information for the candidate terminal. For example, the identification information may include a unique identification number (eg, international mobile equipment identity (IMEI)) of the candidate terminal, a country code (eg, mobile country code (MCC)) of the candidate terminal, or a mobile communication network number (eg, mobile country code) of the candidate terminal. It may include at least one of MNC (mobile network code), an e-mail address of the candidate terminal, and a phone number of the candidate terminal. Here, the location information may include information on location coordinates received by the candidate terminal from a global navigation satellite system (GNSS) and an IP address of the candidate terminal. For example, information about location coordinates may include the latitude, longitude, and altitude of the test taker terminal. In this case, the server may determine a country corresponding to the IP address of the test taker terminal from a prestored list of countries by IP address, and determine the corresponding country as a country for the test taker terminal. Here, the information on the type of mock test may include the test type of the mock test related to the Korean proficiency test and the progress type of the mock test related to the Korean proficiency test. Test types of mock tests related to the Korean Proficiency Test may include a first type including a listening section and a reading section and a second type including a listening section, a reading section, and a writing section. The mock test related to the Korean Proficiency Test may include a first progress type and a second progress type.

For example, in the first progress type and the second progress type, a mock test related to the Korean language proficiency test may be conducted according to a preset progress time. The first progress type is a type in which the authority to determine the opening date and opening time of the online test center is allowed to the test taker terminal, and the test taker terminal is allowed to manipulate the audio file according to the questions in the listening area. The second progress type is a type in which the authority to determine the opening date and opening time of the online test center is allowed to the server, and manipulation of the test taker's terminal for the audio file according to the questions in the listening area is not allowed, like the actual TOPIK. In this case, in the case of the first progress type, a mock test related to the Korean language proficiency test may be conducted at a time set by the test taker terminal. In the case of the second progress type, a mock test related to the Korean Proficiency Test may be conducted at a time set by the server.

For example, the application message may be transmitted together with payment for a mock test related to the Korean proficiency test of the test taker terminal.

In step S302, the server may transmit a guidance message about a mock test related to the Korean language proficiency test requested by the candidate terminal to the candidate terminal based on the application message. Here, the guide message is a message for guiding a mock test related to the Korean proficiency test requested by the test taker terminal. For example, in case of the first progress type, the information message includes the test time and break time for each period for the mock test related to the Korean language proficiency test applied for by the test taker terminal, instructions for each step of the test, and notes for online progress. can do. In the case of the 2nd type, the information message includes the admission time for the mock test related to the Korean language proficiency test that the candidate terminal applied for, test time and break time for each class, guidance for each stage of test progress, and notes for online progress. can do.

For example, based on completion of payment for the mock test related to the test of proficiency in Korean applied by the test taker terminal, the server may transmit a guide message for the mock test related to the test of proficiency in Korean to the test taker terminal. The server may transmit the guide message using a language matching the country identified by the location information of the candidate terminal. For example, if the country identified by the location information of the candidate terminal is Vietnam, the server may transmit the guide message in Vietnamese.

In step S303, the server may create an online test center where a real-time mock test is conducted at a preset opening date and opening time, based on the fact that the mock test related to the Korean language proficiency test corresponds to the second type.

In this case, the server may create an online test site in which real-time mock tests are conducted for the opening country at a preset opening date and opening time. For example, the opening country may be determined based on location information of the test taker terminal. For example, the preset opening date and opening time may be determined based on standard time of a country or region identified by location information of the candidate terminal. For example, if the country identified by the location information of the test taker's terminal is Vietnam, the server may create an online test site for Vietnam on a preset opening date and opening time based on Vietnam's standard time.

The online test center is created on a web page related to the server, and the memory size of the server allocated to the online test center may be different according to the number of test taker terminals that have applied for the real-time mock test.

In step S304, the server may transmit a notice message notifying that the online test center has been opened to the test taker terminal after a first preset time elapses from the preset opening time.

Here, the announcement message is a message informing that an online test center has been opened, and may include a web address of the online test center, test time and break time for each class, and start time for admission to the online test center. For example, the server may transmit the announcement message using a language matching a country identified by location information of the candidate terminal.

For example, the server may test whether the mock test is smoothly conducted in the online test center for a first preset time from a preset opening time. That is, the preset first time may be a time required for stabilization of the server.

Additionally, for example, the first preset time may be determined by Equation 1 below.

은 상기 응시자 단말과 관련된 국가의 가중치이고, 상기 n_a는 상기 모의고사에 신청한 응시자 단말의 개수이고, 상기 n_m은 모의고사에 신청하는 응시자 단말의 평균 개수이고, 상기 t_c는 상기 서버의 시스템을 점검하기 위한 시간이고, 상기

는 상기 모의고사의 유형과 관련된 가중치이고, 상기 k는 상기 모의고사에서 듣기 영역의 문항 개수이고, 상기 t_i는 i번째 듣기 영역의 문항에 대한 음성 파일의 재생시간일 수 있다.In Equation 1, the t ₁ is the preset first time,

is the weight of the country related to the test taker terminal, n _a is the number of test taker terminals applying for the mock test, n _m is the average number of test taker terminals applying for the mock test, and t _c is the system of the server It is time to check, and

is a weight related to the mock test type, k is the number of questions in the listening section of the mock test, and t _i may be a playback time of an audio file for an i-th listening section question.

For example, the weight of the country associated with the test taker terminal may have a different value for each country, and may be pre-stored in the server as a value greater than 0 and less than 2. For example, the weight associated with the type of mock test may have a different value for each type of mock test, and may be pre-stored in the server as a value greater than 0 and smaller than 2. For example, the time for checking the system of the server may be different according to the performance of the server and may be preset in the server. That is, the shorter the average response time according to concurrent users of the server and the greater the number of processes per unit time according to concurrent users, the shorter the time for checking the system of the server. For example, the preset first time may be set longer as the average reproduction time of one listening question is longer and the number of terminals that have applied for the mock test is larger.

Through this, the server can sufficiently secure time required for stabilization of the server in consideration of various variables related to the online mock test, and the server can smoothly conduct the online mock test. In addition, by changing the time flexibly according to the performance of the server and the environment related to the online mock test, rather than a fixed time, it is possible to adaptively secure the time necessary for stabilization of the server.

In step S305, the server may receive an admission message for the online test site from the test taker terminal within a second preset time from the time when the first preset time elapses from the preset opening time.

Here, the admission message is a connection request message for the web address of the online test site by the test taker terminal, and may include identification information of the test taker terminal. The server may establish a connection with the candidate terminal based on the admission message received from the candidate terminal.

For example, the server may determine whether the admission of the test taker terminal is permitted by comparing identification information included in the admission message with identification information pre-stored in the server. For example, the server may allow access of the test taker terminal when there is identification information identical to the identification information included in the admission message among identification information pre-stored in the server. The server may establish a connection with the test taker terminal to which access is permitted.

For example, after a second preset time elapses from the elapse of a preset first time from the preset opening time, the test taker terminal that has transmitted the admission message to the server may not establish a connection with the server. . That is, after a second preset time elapses from the time when the first preset time elapses from the preset opening time, the test taker terminal may not be allowed to access the server.

Additionally, for example, a notification message may be transmitted to the test taker terminal at preset intervals between a time when a first preset time elapses from the preset opening time and a preset second time. Here, the notification message is a message informing the position of the online test center, and may include a web address of the online test center and a mock test start time. For example, the server may transmit a notification message to an e-mail address of the test taker terminal or a phone number of the test taker terminal. For example, the server may not transmit a notification message based on receiving an admission message from the test taker terminal.

Additionally, for example, the server may transmit information on the idle screen to the candidate terminal based on receiving an admission message from the candidate terminal. For example, based on information on the standby screen, a standby screen including a time remaining until a mock test start time may be displayed on the display unit of the test taker terminal.

In steps S306 and S307, the server may provide information on the real-time mock test previously input to the server to the test taker terminal based on the connection between the test taker terminal and the server.

Information on the pre-entered real-time mock test includes problems by area, points assigned to questions by area, fingerprints for questions by area, audio files for questions in the listening area, preliminary instructions by class, preparation instructions, main ordinances, and end ordinances. It may include an audio file, an image file for each domain question, options for each domain question, and a view of the domain question.

For example, when the mock test start time displayed on the standby screen arrives, information about the real-time mock test pre-input into the server may be provided to the test taker terminal through a user interface.

For example, the name of the current area (eg, listening area), the remaining time, the total number of questions, and the number of remaining questions may be displayed through a user interface on the top of the display unit of the test taker terminal where the mock test is being conducted. For example, questions may be displayed through a user interface at the left end of the display unit of the test taker terminal where the mock test is being conducted. For example, an area where options can be marked through a user interface, a problem status area, and a check function button may be displayed on the right end of the display unit of the test taker terminal where the mock test is being conducted. Here, the problem status area may be an area indicating unsolved problems and problems checked by the user. The check function button may be a button having a function of checking a problem that the user wants to put on hold. For example, a previous question button, a next question button, and an answer submission button may be displayed on a lower portion of a display unit of a test taker terminal where a mock test is being conducted through a user interface. The previous question button may be a button having a function of returning to the previous question, the next question button may be a button having a function of moving to the next question, and the answer submission button may be a button having a function of submitting an answer.

For example, based on the connection between the test taker terminal and the server, information about a sound quality type of a voice file for a listening area may be transmitted to the test taker terminal. The sound quality type of the voice file may include a general sound quality type and an actual sound quality type in which the voice file is processed similarly to an actual test hall. For example, the voice file of the real sound quality type may be a voice file in which noise is included in the voice file of the normal sound quality type. The audio file for the listening area may be reproduced as the type of the audio file for the listening area selected by the test taker terminal. Based on the fact that the mock test related to the Korean language proficiency test corresponds to the second progress type, the operation button for the audio file for the listening area may be deactivated. Here, the operation buttons may include a pause button, a rewind button, a random play button, a fast forward button, a previous problem button to return to the previous problem, and a next problem button to move to the next problem.

For example, according to the number of test taker terminals connected to the online test center, the capability of the server, and the communication state between the server and the test taker terminal, the test taker terminal and the server are connected and displayed on the screen of questions transmitted to the test taker terminal. The maximum number of problems can be determined.

Additionally, for example, the maximum number of questions displayed on the screen of questions transmitted to the test taker terminal may be determined by Equation 2 below.

In Equation 2, n _p is the maximum number of questions displayed on the item screen, n is the number of test taker terminals connected to the server, and t _r is the average response time for test taker terminals of the server , wherein n _avg is the average number of test taker terminals connected to the server, t _th is a reference response time, the RSRP is a value related to the communication state of the test taker terminal, and the RSRP _th is a value related to the communication state is a reference value for n, and n _d may be a basic value for the maximum number.

For example, the average number of test taker terminals connected to the server, a reference response time, a reference value for a value related to a communication state, and a default value for the maximum number may be pre-stored values in the server. For example, RSRP (reference signal received power) is a value representing a communication state of a terminal and may have a negative dB value. For example, as the absolute value of RSRP increases, it may be determined that the communication state of the terminal is poor.

For example, the max function is a function that determines the larger of the two values in parentheses, and the ceil function is a function that determines the integer part excluding the decimal point from the value in parentheses as the corresponding value.

Through this, the server determines the maximum number of questions displayed on the screen of questions transmitted to the candidate terminal according to the server's capability and the communication state of the terminal, so that the server can smoothly proceed with the mock exam.

According to an embodiment, based on a user of the test taker terminal performing a hovering operation within a preset height for an option of a question in the question screen of the reading area, the option is displayed in a blank area associated with the option of the question. can be displayed

Here, the hovering operation may be an operation of inputting a command while the user's hand of the candidate terminal is suspended in the air without directly touching the candidate terminal. The option may be displayed in the blank area according to a change in the hovering position. For example, the hovering operation may be performed by a touch pen or a finger. The touch pen has a built-in coil, the display unit of the test taker terminal includes a touch screen, and the touch screen is an EMR (Electro-Magnetic Resonance) type touch panel that senses the touch pen based on mutual electromagnetic induction. can include The touch screen may further include a capacitive touch panel, and the test taker terminal may detect a touch through the capacitive touch panel and a hovering or touch through the EMR touch panel. Also, the hovering operation may include any one of pressing a button formed on the touch pen, tapping the touch pen, moving the touch pen faster than a predetermined speed, and touching an icon.

According to an embodiment, a user interface for selecting a method of inputting an answer to a question screen in the writing area may be provided to the test taker terminal. The method of inputting an answer to the question screen of the writing area may include a first method of inputting an answer using a text field of the test taker terminal and a second method of inputting an image provided by the test taker terminal. The image provided by the test taker terminal may be an image directly written by a user of the test taker terminal. For example, the image directly written by the user of the test taker terminal may include an image written by the user directly on an answer sheet and an image written using a touch pen included in the test taker terminal.

Here, the text field may be a component utilized when a user inputs and confirms text through a user interface.

For example, in the image provided by the test taker terminal, text included in the image may be converted into text data through various Optimal Character Recognition (OCR) methods.

In step S308, the server may receive an answer for each area of the test taker terminal from the test taker terminal.

Additionally, for example, during a break between the test time of the writing area and the test time of the reading area, the server groups a preset number of answers in the writing area, and sequentially sends the answers in the writing area in group units. It can be received from terminals.

Alternatively, for example, the server may group answers to a plurality of writing areas by a preset data size, and sequentially receive answers to the plurality of writing areas from test taker terminals in group units.

At this time, while the candidate terminal transmits the answer in the writing area to the server, the transmission rate for the answer in the writing area is displayed through the user interface on the display unit of the candidate terminal, and the transmission of the answer in the writing area from the candidate terminal to the server is completed. A warning message may be displayed warning not to end transmission until For example, the server may deactivate a button for ending a corresponding screen in the test taker terminal until all answers in the writing area are transmitted. For example, if the answer in the writing area is not normally transmitted due to a network error or the like, a button requesting retransmission may be displayed on the display unit of the test taker terminal through a user interface.

Through this, at the time of submitting the answer to the writing area, which is the time when the largest request occurs to the server during the process of running the overall test, all concurrent accessors transmit the answer submission at once at the end of the test, so the server Traffic may be appropriately distributed by setting a time point for submitting an answer to the writing area differently for each test taker device.

In step S309, the server may determine a score for each section of the test taker's terminal based on the test type of the mock test related to the Korean Proficiency Test and the provisional score for the answer for each section of the candidate's terminal.

A false scoring score for the writing area among the answers for each area of the test taker terminal may be determined through a false scoring model using a first neural network based on the answer to the writing area of the test taker terminal after the real-time mock test is finished.

Among the answers for each area of the test taker terminal, provisional scoring points for the listening area and the reading area may be determined by comparing the answers to the listening area and the reading area of the test taker terminal with answers pre-stored in the server after the real-time mock test is finished. .

For example, based on the fact that the test type corresponds to the second type, provisional scoring points for answers in the writing area of the test taker terminal may be transmitted to the scorer terminal. A final score for an answer in the writing area of the test taker terminal may be transmitted to the server from the scorer terminal. Scores for answers in the writing area of the test taker terminal may be determined as final scores for answers for each area of the test taker terminal. Here, the scorer terminal may be a terminal that scores points for answers in the writing area. The scorer terminal may be the electronic device 101 of FIG. 1 .

The false scoring model may be a gated recurrent unit (GRU)-based neural network. Here, the GRU may be a model modified from a recurrent neural network (RNN).

The first neural network may include a first input layer, one or more first hidden layers, and a first output layer. Data for learning each of the first neural networks consisting of a plurality of texts, a plurality of answer texts, and correct answer points is input to the first input layer of the first neural network, and the one or more first hidden layers and A first output vector is output through one output layer, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value is output using a first loss function that compares the first correct answer vector for the learning data of , and the parameters of the first neural network are learned in a direction in which the first loss value becomes smaller. The false scoring point A model can be created.

According to an embodiment, the expected correction area may be an area where texts corresponding to a plurality of error types are located in an answer to the writing area of the test taker terminal. The plurality of error types may include spaces errors, punctuation errors, rhetorical errors, spelling and grammar errors, letter deletion errors, letter addition errors, letter substitution errors, and letter separation errors. Here, the error about spacing may be an error that violates rules of spacing in a specific language. Punctuation errors can be errors in missing or misplaced punctuation marks between sentences in a particular language. Errors about numerals can be errors about positive numerals indicating quantity and ordinal numerals indicating order. For example, when a specific language is Korean, an error on numeral may correspond to a case where 'eleven: fifty' is misspelled as 'eleven: fifty' or 'ten one: fifty'. Spelling and grammatical errors may be errors that violate the spelling and grammar of a particular language. The character deletion error may be an error in which characters of a specific language are deleted. The character addition error may be an error in which characters of a specific language are added. A letter substitution error may be an error in which a word in a particular language is replaced with another word or the order of phonemes within a syllable is changed.

The correction prediction model may include a bidirectional long short-term memory (LSTM) model. In general, a recurrent neural network (RNN) can effectively model time-series information because hidden layer values for an existing input stored therein are considered in an output for a next input value. However, since RNN is a structure that depends on past observation values, problems such as vanishing gradient or exploding gradient may occur. A model to solve this problem is LSTM, and by replacing nodes inside the LSTM with memory cells, information can be accumulated or some of past information can be deleted, and the problem of the RNN can be supplemented. In addition, the bidirectional LSTM is an LSTM having bidirectionality, and may include a forward LSTM and a backward LSTM. For example, a linear function may be used as an activation function of a forward LSTM, and a sigmoid function may be used as an activation function of a backward LSTM.

The second neural network may include a second input layer, one or more second hidden layers, and a second output layer. Data for learning of each second neural network composed of a plurality of texts and a plurality of texts for each of a plurality of correct answer types is input to the second input layer of the second neural network, and the one or more second hidden A second output vector is output through a layer and a second output layer, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is used as the second output vector. A second loss value is output using a second loss function that compares a vector with a second correct answer vector for each learning data, and parameters of the second neural network are learned in a direction in which the second loss value decreases. , the correction prediction model may be generated.

For example, data for each of a plurality of error types may be pre-stored in the server through various methods such as crowd sourcing.

Specifically, the additive prediction model may include an embedding and encoder unit, a second neural network including a bidirectional LSTM, and an attention layer.

A vector input to the second neural network including the bidirectional LSTM may be a vector output by passing a plurality of texts through an embedding and encoder unit. For example, the embedding and encoder unit may include a plurality of token embedding layers, a plurality of position embedding layers, and an encoder. For example, the plurality of texts may be text data for answers to writing areas of a plurality of test taker terminals.

The token embedding layer may convert input text preprocessed with a tokenizer for a plurality of texts into a token vector including tokens. For example, a token vector obtained by tokenizing a sentence into a plurality of morphemes may be generated by preprocessing a plurality of texts with a tokenizer through a token embedding layer. Here, the morpheme means the smallest unit of speech that cannot be further analyzed as an element having meaning.

In addition, by using a masked language model for the token vector, the encoder inserts the entire sentence through the given sequence into the model, then predicts and learns the word corresponding to the blank, and after learning the sentence, The corresponding sentence is displayed as a series of tokens, and the part to be blank in the token array can be set as a mask.

The position embedding layer may add a position embedding vector indicating a position of each morpheme to a token vector obtained by tokenizing one sentence into a plurality of morphemes. Here, the token vector may be converted into a Q vector representing a query, a K vector representing a key, and a V vector representing a value.

At this time, the server may determine a pair of word relationship through the position embedding layer. For example, to determine the closeness of each word, the server can use scaled dot-product attention. The server may determine a pair of word relationships by Equation 3 below based on scaled inner product attention.

In Equation 3, Q is a vector for the hidden state of the previous layer of the decoder, K is a vector for the output state of the encoder, V is a vector for the output state of the encoder, and dk is the dimension of the K vector. can That is, Q may be the token of the affected decoder, K may be the token of the influencing encoder, and V may be the token of the encoder to be multiplied by the weight for the influence.

That is, the server can determine a pair of matrices for words in a sentence by dividing the dot-product of Q and K using the cosine similarity by the square root of the dimension of the K vector and applying a softmax function. there is.

For example, the one or more second hidden layers include one or more forward LSTM blocks and one or more reverse LSTM blocks, and each LSTM block includes a memory cell, an input gate, and an erase gate , may include an output gate.

The server may input a pair of matrices of words in the sentence to the bidirectional LSTM, and input the vectors output through the bidirectional LSTM to the attention layer. At this time, the server can fine-tune the correction prediction model by connecting the hidden token through bidirectional LSTM.

The attention layer can input and output information from one sentence to the end of the sentence, and can process the first word to form a correlation with words farther away. Thereafter, the output layer may determine a word having the highest probability based on text data for each of a plurality of error types as an output value through a softmax function.

That is, the server learns a correction prediction model including a bidirectional LSTM model based on a plurality of texts, and selects an area corresponding to at least one of a plurality of error types in the text data in the answer to the writing area through the correction prediction model. can decide The server may underline an area corresponding to at least one of the plurality of error types and transmit an answer to the writing area to the appender terminal. Here, the corrector terminal may be a terminal that corrects and corrects answers to mock tests related to the Korean Proficiency Test. The appender terminal may be the electronic device 101 of FIG. 1 .

Through this, it is possible to assist the corrector terminal to more easily correct and delete answers to the writing area.

In step S310, the server may transmit scores for answers for each area of the test taker terminal to the test taker terminal.

For example, the server may transmit, to the test taker terminal, an answer to a problem for each area, a commentary on the problem for each area, and a model answer to the problem for each area, along with scores for answers for each area of the test taker terminal.

According to an embodiment, when the test type corresponds to the second type, and an option to edit an answer to a writing area is included in paid options for the test taker terminal identified according to the identification information of the test taker terminal. , An answer to the writing area of the test taker terminal in which the expected correction/removal area is displayed may be transmitted from the server to the corrector terminal. Here, the paid option may refer to a plurality of additional services that the upper extremity test taker terminal applies for by paying a fee when applying for a mock test. A correction copy for the writing area may be received from the server by the correction person terminal. An edited version of the writing area may be transmitted from the server to the candidate terminal. The predicted correction area may be determined through an correction prediction model using a second neural network based on an answer to the writing area of the test taker terminal.

Through this, the corrector's terminal receives the area where correction is expected in advance, so that it can more easily proceed with the correction for the answer.

Additionally, or, for example, the corrector terminal may transmit the correction copy for the writing area to the inspector terminal. The inspector terminal may inspect the edited copy of the writing area to see if there are any abnormalities, and transmit the edited copy of the writing area for which the inspection is completed to the server. Here, the inspector terminal is a terminal that inspects the edited copy for the writing area, and may be the electronic device 101 of FIG. 1 . Through this, by checking the answer to the writing area once more, it is possible to provide higher quality feedback to the test taker terminal.

4 is a diagram of a false scoring model according to an embodiment. The embodiment of FIG. 4 can be combined with various embodiments of the present disclosure.

Referring to FIG. 4 , the first neural network used in the false scoring model may be a GRU-based neural network. The false scoring model may include an embedding and encoder unit, a first neural network based on a GRU, and an attention layer.

The first neural network may include a first input layer 410 , one or more first hidden layers 420 and a first output layer 430 .

For example, the plurality of first input vectors, the plurality of second input vectors, the plurality of third input vectors, and the plurality of fourth input vectors input to the first neural network may be vectors output through an embedding and encoder unit. there is. For example, the embedding and encoder unit may include a plurality of token embedding layers, a plurality of position embedding layers, and an encoder. Here, the plurality of second input vectors to the plurality of fourth input vectors may be input vectors classified according to scores.

The token embedding layer may convert input text preprocessed with a tokenizer for a plurality of first texts, a plurality of second texts, a plurality of third texts, and a plurality of fourth texts into a token vector including tokens. there is. For example, the plurality of first texts may be text data for answers to the writing areas of the plurality of test taker terminals, and the plurality of second texts to the plurality of fourth texts may be a plurality of answer texts classified according to scores. there is. For example, the plurality of second texts may include texts of answers classified as high scores. For example, the plurality of third texts may include texts of answers classified as intermediate scores. For example, the plurality of fourth texts may include texts of answers classified as low scores. In the present disclosure, scores may be classified in more various ways, but are not limited thereto.

For example, a token vector obtained by tokenizing one sentence into a plurality of morphemes may be generated by pre-processing a plurality of first texts and a plurality of second texts with a tokenizer through a token embedding layer. Here, the morpheme means the smallest unit of speech that cannot be further analyzed as an element having meaning. In addition, by using a masked language model for the token vector, the encoder inserts the entire sentence through the given sequence into the model, then predicts and learns the word corresponding to the blank. Marked as a token, the part to set as a blank in the token array can be set as a mask.

The position embedding layer may add a position embedding vector indicating a position of each morpheme to a token vector obtained by tokenizing one sentence into a plurality of morphemes. Here, the token vector may be converted into a Q vector representing a query, a K vector representing a key, and a V vector representing a value.

At this time, the server may determine a pair of word relationship through the position embedding layer. For example, to determine the closeness of each word, the server can use scaled inner product attention. The server may determine a pair of word relationships based on the scaled inner product attention by Equation 3 described above. That is, the server can determine a pair of matrices for words in a sentence by dividing the dot-product of Q and K using the cosine similarity by the square root of the dimension of the K vector and applying a softmax function. there is.

)가 활성화 함수인 레이어일 수 있다. 예를 들어, 리셋 게이트 및 업데이트 게이트를 통해 히든 스테이트가 제어되고, 각 게이트와 입력에 따른 가중치들이 존재할 수 있다.For example, the one or more first hidden layers may include one or more GRU blocks, and one GRU block may include a reset gate and an update gate. Here, the reset gate and the update gate may include sigmoid layers. For example, a sigmoid layer is a sigmoid function (

) may be a layer whose activation function is For example, the hidden state may be controlled through a reset gate and an update gate, and weights according to each gate and input may exist.

The reset gate resets past information, and the weight r(t) derived through the previous hidden layer can be determined by Equation 4.

For example, a plurality of first input vectors, a plurality of second input vectors, a plurality of third input vectors, and a plurality of fourth input vectors are input to the input layer, and the reset gate includes a plurality of first input vectors; When the current input value (x _t ) generated based on the plurality of second input vectors, the plurality of third input vectors, and the plurality of fourth input vectors is input, the dot product with the weight W _r at the current time is performed, and the plurality of second input vectors The hidden state (h _{(t-1) )} of the previous time, generated based on the first input vector, the plurality of second input vectors, the plurality of third input vectors, and the plurality of fourth input vectors, is the weight U _r of the previous time. And finally, the sum of the two values is input to the sigmoid function, and the result can be output as a value between 0 and 1. Through the value between 0 and 1, it may be determined how much to utilize the hidden state value of the previous time.

The update gate determines the update rate for past and present information, and z(t) is the amount of information at the current time, which can be determined by Equation 5.

For example, if the input value (x _t ) at the current time is input, the dot product is performed with the weight W _z at the current time, and the hidden state (h _(t-1) ) at the previous time is the dot product with the weight U _z at the previous time. Finally, by adding the two values and inputting them to the sigmoid function, the result can be output as a value between 0 and 1. Further, 1-z(t) may be multiplied by information (h _(t-1) ) of the hidden layer at the previous point in time.

Through this, z(t) can reflect how much current information will be used and how much 1-z(t) will be used for past information.

By multiplying the result of the reset gate, the information candidate group of the current time point t can be determined by Equation 6.

For example, if the input value (x _t ) at the current time is input, the dot product of the weight W _h at the current time and the hidden state (h _(t-1) ) at the previous time is the weight U _h at the previous time It can be input to the tanh function by adding the dot product and multiplying by r(t). For example, tanh means a nonlinear activation function (hyperbolic tangent function).

By combining the result of the update gate and the candidate group, the weight of the hidden layer at the current time can be determined by Equation 7.

For example, the value obtained by multiplying the output value z(t) of the update gate by the current hidden state (h(t)), the value 1-z(t) discarded from the update gate, and the hidden state (h( The weight of the hidden layer at the current time may be determined as the sum of values multiplied by t-1)).

For example, the weight initialization for the neural network used in the pseudo-scoring model is, for each layer, the weight obtained by dividing the sum of the number of input values input to the corresponding layer and the number of output values output from the corresponding layer can be performed based on Accordingly, the start point of the weight may be set to a value within an appropriate range.

For example, dropout may be applied to a neural network used in the false scoring model. Here, dropout is a technique of removing neurons with a probability between 0 and 1 from layers connected to each other. For example, the dropout ratio may be set to 0.5. In this case, if there are 4 neurons in a specific layer, each of the 4 neurons may be randomly removed with a probability of 0.5. Through this, overfitting to the false scoring model can be prevented.

The server may input the output vector to the attention layer. The attention layer can input and output information from one sentence to the end of the sentence, and can process the first word to form a correlation with words farther away. Then, the output layer may determine a word having the highest probability as an output value through a softmax function.

Therefore, the parameters of the neural network learned through the false scoring model can be used, and the false scoring model determines the false scoring score for the answer in the writing area of the test taker terminal based on the text data of the answer for the writing area of the test taker terminal. can

5 is a flowchart of a method for a server to provide a mock test service to a test taker terminal using a neural network according to an embodiment. The embodiment of FIG. 5 can be combined with various embodiments of the present disclosure.

Referring to FIG. 5 , in step S501, the server may create an online test center where a real-time mock test is conducted at a preset opening date and opening time.

In step S502, the server may determine whether the test taker terminal accesses within a first preset time from a preset opening time. For example, the server may determine that the test taker terminal has accessed based on receiving an admission message from the test taker terminal.

In step S503, when the test taker terminal accesses within the preset first time, the server may transmit a notice message to the test taker terminal after the preset first time elapses.

In step S504, the server may determine whether the test taker terminal accesses within a second preset time from the time when the first preset time elapses from the preset opening time. For example, the server may determine that the test taker terminal has accessed based on receiving an admission message from the test taker terminal.

In step S505, if the test taker terminal does not access within a second preset time from the time when the first preset time has elapsed from the preset opening time, the server may transmit a guide message about the connection failure to the test taker terminal. Here, the guide message for inability to access is a message informing that access will not be possible until the mock test at the online test site ends, and may include the time when the mock test for the online test taker ends.

In step S506, the server may set a voice file for listening questions based on the information about the type of voice file for the listening area received from the test taker terminal.

In step S507, the server may transmit information about the test taker guidance and standby screen to the test taker terminal. Here, the guide message for the candidate may include, for example, test time and break time for each class, information on each stage of test progress, and notes on online progress. Based on the information on the standby screen, a standby screen including the time remaining until the mock test start time may be displayed on the display unit of the test taker terminal.

In step S508, the server may transmit question screens for each area according to the number of questions per screen. The maximum number of questions displayed on the screen of questions transmitted to the test taker terminal may be determined by Equation 2 below. For example, the number of questions per screen is less than or equal to the maximum number of questions displayed on the question screen, and may be the number of questions displayed on the question screen selected by the test taker terminal.

In step S509, the server may determine whether the test taker terminal uses a text field when preparing an answer to the writing area. For example, the server may provide the test taker terminal with a user interface for selecting a method of inputting an answer to a question screen in the writing area. The method of inputting an answer to the question screen of the writing area may include a first method of inputting an answer using a text field of the test taker terminal and a second method of inputting an image provided by the test taker terminal. The image provided by the candidate terminal may be an image directly written by a user of the candidate terminal.

In step S510, when the test taker terminal uses the text field, the server may receive information about an answer for each area including an answer text for the writing area from the test taker terminal.

In step S511, when the test taker terminal does not use the text field, the server may receive information about an answer for each area including an answer image for the writing area from the test taker terminal.

In step S512, the server may transmit a notification set 5 minutes before the end of the mock test conducted in the online test center to the test taker terminal. For example, the notification may be preset by the test taker terminal. The notification may be any one of a type in which the screen of the test taker's terminal flickers or a notification sound is output through an output unit of the test taker's terminal.

In step S513, the server may determine a score for an answer for each area and transmit the score for the answer for each area to the test taker terminal.

After the real-time mock test is over, the server compares the answers to the listening and reading areas of the test taker terminal with the answers pre-stored in the server to determine provisional scoring points for the listening and reading areas among the answers for each area of the test taker terminal. there is. Thereafter, if there is no answer that has been objected to by the test taker terminal and an answer recognized as an incorrect answer among the answers pre-stored in the server, the server listens to the points for the listening area and the reading area among the answers for each area of the test taker terminal. It can be determined by the score for the domain and reading domain.

After the real-time mock test is finished, the server may determine a provisional scoring score for the writing area among the answers for each area of the test taker terminal through a provisional scoring model using the first neural network based on the answer to the writing area of the test taker terminal. For example, based on the fact that the test type corresponds to the second type, provisional scoring points for answers in the writing area of the test taker terminal may be transmitted to the scorer terminal. A final score for an answer in the writing area of the test taker terminal may be transmitted to the server from the scorer terminal. Scores for answers in the writing area of the test taker terminal may be determined as final scores for answers for each area of the test taker terminal.

Through this, the scorer terminal may more objectively determine the final score for the answer in the writing area by referring to the provisional score.

In step S514, the server may determine whether the test taker terminal has paid for the paid option. For example, the server may determine whether an option for adding or subtracting an answer to a writing area is included in paid options for the candidate terminal identified according to the identification information of the candidate terminal.

In step S515, when the test taker terminal pays for the paid option, the server may display an area expected to be corrected or deleted for an answer in the writing area. The expected correction area may be an area where texts corresponding to a plurality of error types are located in an answer to the writing area of the test taker terminal. The predicted correction area may be determined through an correction prediction model using a second neural network based on an answer to the writing area of the test taker terminal.

In step S516, the server transmits the answer in the writing area indicating the expected correction area to the corrector terminal, so that the answer in the writing area can be corrected and corrected, and the corrector terminal can correct the answer in the writing area. By transmitting to the inspector terminal, inspection of the edited copy can be performed.

In step S517, the server may transmit an edited copy of the answer in the writing area to the test taker terminal. The corrected copy of the answer in the writing area may be a corrected copy that has been inspected by the inspector's terminal.

In step S518, if the test taker's terminal does not pay for the paid option, the server may transmit an correction publicity message promoting an correction service for an answer in the writing area to the test taker's terminal.

6 is a block diagram illustrating a configuration of a server according to an exemplary embodiment. One embodiment of FIG. 6 may be combined with various embodiments of the present disclosure.

As shown in FIG. 6 , the server 600 may include a processor 610 , a communication unit 620 and a memory 630 . However, not all components shown in FIG. 6 are essential components of the server 600 . The server 600 may be implemented with more components than those shown in FIG. 6, or the server 600 may be implemented with fewer components than those shown in FIG. For example, the server 600 according to some embodiments may further include a user input interface (not shown), an output unit (not shown), etc. in addition to the processor 610, the communication unit 620, and the memory 630. .

Processor 610, typically controls the overall operation of the server (600). The processor 610 may include one or more processors to control other elements included in the server 600 . For example, the processor 610 may generally control the communication unit 620 and the memory 630 by executing programs stored in the memory 630 . Also, the processor 610 may perform the functions of the server 600 described in FIGS. 3 to 5 by executing programs stored in the memory 630 .

The communication unit 620 may include one or more components that allow the server 600 to communicate with other devices (not shown) and servers (not shown). The other device (not shown) may be a computing device such as the server 600 or a sensing device, but is not limited thereto. The communication unit 620 may receive a user input from another electronic device or data stored in an external device from an external device through a network.

The memory 630 may store programs for processing and controlling the processor 610 . For example, the memory 630 may store information input to a server or information received from another device through a network. Also, the memory 630 may store data generated by the processor 610 . The memory 630 may store information input to or output from the server 600 .

The memory 630 may be a flash memory type, a hard disk type, a multimedia card micro type, a card type memory (eg SD or XD memory, etc.), RAM (RAM, Random Access Memory) SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk , an optical disk, and at least one type of storage medium.

The embodiments described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA). array), programmable logic units (PLUs), microprocessors, or any other device capable of executing and responding to instructions. A processing device may run an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of software. For convenience of understanding, there are cases in which one processing device is used, but those skilled in the art will understand that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that it can include. For example, a processing device may include a plurality of processors or a processor and a controller. Other processing configurations are also possible, such as parallel processors.

Software may include a computer program, code, instructions, or a combination of one or more of the foregoing, which configures a processing device to operate as desired or processes independently or collectively. The device can be commanded. Software and/or data may be any tangible machine, component, physical device, virtual equipment, computer storage medium or device, intended to be interpreted by or provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. Software may be distributed on networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer readable media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. Program commands recorded on the medium may be specially designed and configured for the embodiment or may be known and usable to those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floptical disks. - includes hardware devices specially configured to store and execute program instructions, such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, as well as machine language codes such as those produced by a compiler. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, the described techniques may be performed in an order different from the method described, and/or components of the described system, structure, device, circuit, etc. may be combined or combined in a different form than the method described, or other components may be used. Or even if it is replaced or substituted by equivalents, appropriate results can be achieved.

Therefore, other implementations, other embodiments, and equivalents of the claims are within the scope of the following claims.

Claims (5)

In a method in which a server provides a mock test service to a test taker terminal using a neural network,
Receiving an application message requesting a mock test related to the Korean language proficiency test from a test taker terminal;
The application message includes identification information of the candidate terminal, location information of the candidate terminal, and information about the type of mock test,
The information on the type of mock test includes the type of mock test related to the Korean Proficiency Test and the type of mock test related to the Korean Proficiency Test,
The mock test related to the Korean Proficiency Test includes a first type including a listening section and a reading section and a second type including a listening section, a reading section, and a writing section,
The proceeding type of the mock test related to the Korean language proficiency test includes a first proceeding type and a second proceeding type, and the first proceeding type allows the test taker terminal to determine the opening date and opening time of the online test center. , In the second progress type, the authority to determine the opening date and opening time for the online test center is allowed to the server,
Based on the fact that the mock test related to the Korean language proficiency test corresponds to the second type, creating an online test center where a real-time mock test is conducted at a preset opening date and opening time;
Transmitting a notice message informing that the online test center has been opened to the test taker terminal after a first preset time has elapsed from the preset opening time;
Receiving an admission message for the online test site from the test taker terminal within a second preset time from the preset opening time;
based on the connection between the test taker terminal and the server, providing information on a real-time mock test input in advance to the server to the test taker terminal;
receiving an answer for each area of the test taker terminal from the test taker terminal;
determining a score for each area of the test taker terminal based on a test type of a mock test related to the Korean language proficiency test and a provisional scoring score for each area of the test taker terminal; and
Transmitting scores for answers for each area of the test taker terminal to the test taker terminal,
A provisional scoring score for the writing area among the answers for each area of the test taker terminal is determined through a provisional scoring model using a first neural network based on the answer to the writing area of the test taker terminal after the real-time mock test is finished,
Based on the fact that the test type corresponds to the second type, and that the paid option for the test taker terminal identified according to the identification information of the test taker terminal includes an option to correct the answer to the write area, the correction expected area The displayed answer to the write area of the test taker terminal is transmitted from the server to the appender terminal,
The correction copy for the writing area is received from the correction person terminal to the server,
An edited copy of the writing area is transmitted from the server to the candidate terminal;
The correction prediction area is determined through an correction prediction model using a second neural network based on an answer to the writing area of the test taker terminal;
Based on the connection between the test taker terminal and the server, information on a type of a voice file for a listening area is transmitted to the test taker terminal;
The type of the voice file includes a general sound quality type and an actual sound quality type in which the voice file is processed similarly to an actual test hall,
The audio file for the listening area is played as the type of the audio file for the listening area selected by the test taker terminal;
Based on the fact that the mock test related to the Korean language proficiency test corresponds to the second progress type, the operation button for the audio file for the listening area is disabled,
The maximum number of questions displayed on the screen of questions transmitted to the test taker terminal after the test taker terminal and the server are connected according to the number of test taker terminals connected to the online test center, the capability of the server, and the communication state between the server and the test taker terminal. number is determined
During the resting time between the test time of the writing area and the test time of the reading area, a preset number of answers for the writing area are grouped, and the answers for the preset number of writing areas are sequentially grouped from test taker terminals. received,
The preset first time is determined by the following equation,

In the above formula, the t ₁ is the preset first time,

is the weight of the country related to the test taker terminal, n _a is the number of test taker terminals applying for the mock test, n _m is the average number of test taker terminals applying for the mock test, and t _c is the system of the server It is time to check, and

is a weight related to the type of mock test, k is the number of questions in the listening area in the mock test, and t _i is a playback time of an audio file for an item in the ith listening area,
method.
delete delete According to claim 1,
Based on the user of the test taker terminal performing a hovering operation within a preset height for the question option on the question screen of the reading area, the option is displayed in a blank area associated with the question option,
A user interface for selecting a method of inputting an answer to a question screen in the writing area is provided to the test taker terminal;
The method of inputting an answer to the question screen of the writing area includes a first method of inputting an answer using a text field of the test taker terminal and a second method of inputting an image provided by the test taker terminal;
The image provided by the test taker terminal is an image directly written by the user of the test taker terminal.
method.
According to claim 1,
Based on the fact that the test type corresponds to the second type, provisional scoring scores for answers in the writing area of the test taker terminal are transmitted to a scorer terminal;
The final score for the answer in the writing area of the test taker terminal is transmitted from the scorer terminal to the server;
The score for the answer in the writing area of the test taker terminal is determined as the final score for the answer for each area of the test taker terminal;
The false scoring model is a gated recurrent unit (GRU) based neural network model,
The first neural network includes a first input layer, one or more first hidden layers and a first output layer;
Data for learning each of the first neural networks consisting of a plurality of texts, a plurality of answer texts, and correct answer points is input to the first input layer of the first neural network, and the one or more first hidden layers and A first output vector is output through one output layer, the first output vector is input to a first loss function layer connected to the first output layer, and the first loss function layer is connected to the first output vector. A first loss value is output using a first loss function that compares the first correct answer vector for the learning data of , and the parameters of the first neural network are learned in a direction in which the first loss value becomes smaller. The false scoring point model is created,
The expected correction area is an area where text corresponding to a plurality of error types is located in the answer to the writing area of the test taker terminal;
The plurality of error types include spacing errors, punctuation errors, rhetorical errors, spelling and grammar errors, letter deletion errors, letter addition errors, letter substitution errors, and letter separation errors,
The additive prediction model includes a bidirectional long short-term memory (LSTM) model,
The second neural network includes a second input layer, one or more second hidden layers, and a second output layer;
Data for learning of each second neural network composed of a plurality of texts and a plurality of texts for each of a plurality of correct answer types is input to the second input layer of the second neural network, and the one or more second hidden A second output vector is output through a layer and a second output layer, the second output vector is input to a second loss function layer connected to the second output layer, and the second loss function layer is used as the second output vector. A second loss value is output using a second loss function that compares a vector with a second correct answer vector for each learning data, and parameters of the second neural network are learned in a direction in which the second loss value decreases. , where the correction prediction model is generated,
method.

Images